# TAMIS: Tailored Membership Inference Attacks on Synthetic Data

arXiv: https://arxiv.org/abs/2504.00758 · HTML: https://mlsanity.com/paper/2504.00758/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Membership inference attacks, one of 12 directions in LLM safety and security.
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Placed in

- LLM safety and security / [Membership inference attacks](https://mlsanity.com/safety/membership-inference-attacks/)

## Builds on (most cited first, 9 of 9)

- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Reconstruction and Membership Inference Attacks against Generative Models](https://mlsanity.com/paper/1906.03006/) (2019)
- [Winning the NIST Contest: A scalable and general approach to differentially private synthetic data](https://mlsanity.com/paper/2108.04978/) (2021)
- [Membership Inference Attacks against Synthetic Data through Overfitting Detection](https://mlsanity.com/paper/2302.12580/) (2023)
- [A Unified Framework for Quantifying Privacy Risk in Synthetic Data](https://mlsanity.com/paper/2211.10459/) (2022)
- [ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Models](https://mlsanity.com/paper/2405.17724/) (2024)
- [Privacy Vulnerabilities in Marginals-based Synthetic Data](https://mlsanity.com/paper/2410.05506/) (2024)
- [A Framework for Auditable Synthetic Data Generation](https://mlsanity.com/paper/2211.11540/) (2022)
- [High Epsilon Synthetic Data Vulnerabilities in MST and PrivBayes](https://mlsanity.com/paper/2402.06699/) (2024)

## Built on by (most cited first, 1 of 1)

- [Disparate Impact in Synthetic Data Generation](https://mlsanity.com/paper/2606.13105/) (2026)

## Abstract (arXiv)

Membership Inference Attacks (MIA) enable to empirically assess the privacy of a machine learning algorithm. In this paper, we propose TAMIS, a novel MIA against differentially-private synthetic data generation methods that rely on graphical models. This attack builds upon MAMA-MIA, a recently-published state-of-the-art method. It lowers its computational cost and requires less attacker knowledge. Our attack is the product of a two-fold improvement. First, we recover the graphical model having generated a synthetic dataset by using solely that dataset, rather than shadow-modeling over an auxiliary one. This proves less costly and more performant. Second, we introduce a more mathematically-grounded attack score, that provides a natural threshold for binary predictions. In our experiments, TAMIS achieves better or similar performance as MAMA-MIA on replicas of the SNAKE challenge.